Views
No views yet
| 数据集 | 训练集 | 验证集 | 测试集 | 任务类型 | 语料来源 |
|---|---|---|---|---|---|
| CEMRNER | 965 | 138 | 276 | 命名实体识别 | 医渡云 |
| CMTNER | 14000 | 2000 | 4000 | 命名实体识别 | CHIP2020 |
| CMedQQ | 14000 | 2000 | 4000 | 句对识别 | 平安医疗 |
| CCTC | 26837 | 3834 | 7669 | 句子分类 | CHIP2019 |
| 模型 | CEMRNER | CMTNER | CMedQQ | CCTC |
|---|---|---|---|---|
| BERT | 81.17% | 65.67% | 87.77% | 81.62% |
| MC-BERT | 80.93% | 66.15% | 89.04% | 80.65% |
| PCL-BERT | 81.58% | 67.02% | 88.81% | 80.27% |
| MedBERT | 82.29% | 66.49% | 88.32% | 81.77% |
| MedBERT-wwm | 82.60% | 67.11% | 88.02% | 81.72% |
| MedBERT-kd | 82.58% | 67.27% | 89.34% | 80.73% |
| - | - | - | - | - |
| Albert | 79.98% | 62.42% | 86.81% | 79.83% |
| MedAlbert | 81.03% | 63.81% | 87.56% | 80.05% |
| MedAlbert-wwm | 81.28% | 64.12% | 87.71% | 80.46% |
杨飞洪,王序文,李姣.BERT模型在中文临床自然语言处理中的应用探索与研究[EB/OL].https://github.com/trueto/medbert, 2021-03.